Library

Video Player is loading.
 
Current Time 0:00
Duration 11:19
Loaded: 0.00%
 
x1.00


Back

Games & Quizzes

Training Mode - Typing
Fill the gaps to the Lyric - Best method
Training Mode - Picking
Pick the correct word to fill in the gap
Fill In The Blank
Find the missing words in a sentence Requires 5 vocabulary annotations
Vocabulary Match
Match the words to the definitions Requires 10 vocabulary annotations

You may need to watch a part of the video to unlock quizzes

Don't forget to Sign In to save your points

Challenge Accomplished

PERFECT HITS +NaN
HITS +NaN
LONGEST STREAK +NaN
TOTAL +
- //

We couldn't find definitions for the word you were looking for.
Or maybe the current language is not supported

  • 00:16

    Hi! Welcome back to Data Mining with Weka.

  • 00:19

    This is Class 2.

  • 00:21

    In the first class, we downloaded Weka and we looked around the Explorer and a few datasets;

  • 00:28

    we used a classifier, the J48 classifier;

  • 00:31

    we used a filter to remove attributes and to remove some instances;

  • 00:37

    we visualized some data—we visualized classification errors on a dataset;

  • 00:45

    and along the way we looked at a few datasets, the weather data, both the nominal and numeric

  • 00:50

    version, the glass data, and the iris dataset.

  • 00:55

    This class is all about evaluation.

  • 00:58

    In Lesson 1.4, we built a classifier using J48.

  • 01:03

    In this first lesson of the second class, we're going to see what it's like to actually

  • 01:09

    be a classifier ourselves.

  • 01:11

    Then, later on in subsequent lessons in this class, we're going to look at more about evaluation,

  • 01:17

    training and testing, baseline accuracy and cross-validation.

  • 01:23

    First of all, we're going to see what it's like to be a classifier.

  • 01:27

    We're going to construct a decision tree ourselves, interactively.

  • 01:30

    I'm going to just open up Weka here.

  • 01:32

    The Weka Explorer.

  • 01:35

    I'm going to load the segment-challenge dataset.

  • 01:43

    segment-challenge.arff -- that's the one I want.

  • 01:50

    We're going to look at this dataset.

  • 01:52

    Let's first of all look at the class.

  • 01:56

    The class values are brickface, sky, foliage, cement, window, path, and grass.

  • 02:04

    It looks like this is kind of an image analysis dataset.

  • 02:07

    When we look at the attributes, we see things like the centroid of columns and rows, pixel

  • 02:15

    counts, line densities, means of intensities, and various other things.

  • 02:23

    Saturation, hue, and the class, as I said before, is different kinds of texture: bricks,

  • 02:30

    sky, foliage, and so on.

  • 02:33

    That's the segment challenge dataset.

  • 02:37

    I'm going to select the user classifier.

  • 02:42

    The user classifier is a tree classifier.

  • 02:45

    We'll see what it does in just a minute.

  • 02:48

    That's the user classifier.

  • 02:53

    Before I start, this is really quite important.

  • 02:58

    I'm going to use a supplied test set.

  • 03:00

    I'm going to set the test set, which is used to evaluate the classifier to be segment-test.

  • 03:13

    The training set is segment-challenge, the test set is segment-test.

  • 03:20

    Now we're all set.

  • 03:23

    I'm going to start the classifier.

  • 03:29

    What we see is a window with two panels: the Tree Visualizer and the Data Visualizer.

  • 03:36

    Let's start with the Data Visualizer.

  • 03:40

    We looked at visualization in the last class, how you can select different attributes for

  • 03:46

    the x and y.

  • 03:48

    I'm going to plot the region-centroid-row against the intensity-mean.

  • 04:09

    That's the plot I get.

  • 04:21

    Now, we're going to select a class.

  • 04:26

    I'm going to select Rectangle.

  • 04:33

    If I draw out with my mouse a rectangle here, I'm going to have a rectangle that's pretty

  • 04:43

    well pure reds, as far as I can see.

  • 04:48

    I'm going to submit this rectangle.

  • 04:54

    You can see that that area has gone and the picture has been rescaled.

  • 04:59

    I'm building up a tree here.

  • 05:00

    If I look at the Tree Visualizer, I've got a tree.

  • 05:09

    We've split on these two attributes, region-centroid-row and intensity-mean.

  • 05:15

    Here we've got sky, these are all sky classes.

  • 05:19

    Here we've got a mixture of brickface, foliage, cement, window, path, and grass.

  • 05:23

    We're kind of going to build up this tree.

  • 05:26

    What I want to do is to take this node and refine it a bit more.

  • 05:30

    Here is the Data Visualizer again.

  • 05:32

    I'm going to select a rectangle containing these items here, and submit that.

  • 05:41

    They've gone from this picture.

  • 05:44

    You can see that here, I've created this split, another split on region-centroid-row and

  • 05:53

    intensity-mean, and here, this is almost all path.

  • 05:55

    233 path instances, and then a mixture here.

  • 06:01

    This is a pure node we've got over there.

  • 06:03

    This is almost a pure node.

  • 06:05

    This is the one I want to work on.

  • 06:07

    I'm going to cover some of those instances now.

  • 06:11

    Let's take this lot here and submit that.

  • 06:15

    Then I'm going to take this lot here and submit that.

  • 06:23

    Maybe I'll take those ones there and submit that.

  • 06:30

    This little cluster here seems pretty uniform.

  • 06:33

    Submit that.

  • 06:34

    I haven't actually changed the axes, but, of course, at any time, I could change these

  • 06:38

    axes to better separate the remaining classes.

  • 06:43

    I could kind of mess around with these.

  • 06:45

    Actually, a quick way to do it is to click here on these bars.

  • 06:51

    Left click for x and right click for y.

  • 06:55

    I can quickly explore different pairs of axes to see if I can get a better split.

  • 07:07

    Here's the tree I've created.

  • 07:08

    I'm going to fit it to the screen.

  • 07:11

    It looks like this.

  • 07:12

    You can see that we have successively elaborated down this branch here.

  • 07:18

    When I finish with this, I can accept the tree.

  • 07:26

    Actually, before I do that, let me just show you that we were selecting rectangles here,

  • 07:33

    but I've got other things I can select: a polygon or a polyline.

  • 07:37

    If I don't want to use rectangles, I can use polygons or polylines.

  • 07:43

    If you like, you can experiment with those to select different shaped areas.

  • 07:51

    There's an area I've got selected I just can't quite finish it off.

  • 07:58

    Alright, I right clicked to finish it off.

  • 08:03

    I could submit that.

  • 08:04

    I'm not confined to rectangles;

  • 08:06

    I can use different shapes.

  • 08:08

    I'm not going to do that.

  • 08:10

    I'm satisfied with this tree for the moment.

  • 08:12

    I'm going to accept the tree.

  • 08:13

    Once I do this, there is no going back, so you want to be sure.

  • 08:18

    If I accept the tree, "Are you sure?" -- yes.

  • 08:21

    Here, I've got a confusion matrix, and I can look at the errors.

  • 08:26

    My tree classifies 78% of the instances correctly, nearly 79% correctly, and 21% incorrectly.

  • 08:35

    That's not too bad, especially considering how quickly I built that tree.

  • 08:42

    It's over to you now.

  • 08:44

    I'd like you to play around and see if you can do better than this by spending a little

  • 08:49

    bit longer on getting a nice tree.

  • 08:52

    I'd like you to reflect on a couple of things.

  • 08:56

    First of all, what strategy you're using to build this tree.

  • 08:59

    Basically, we're covering different regions of the instance space, trying to get pure

  • 09:04

    regions to create pure branches.

  • 09:07

    This is kind of like a bottom-up covering strategy.

  • 09:10

    We cover this area and this area and this area.

  • 09:15

    That's not how J48 works.

  • 09:17

    When it builds its trees, it tries to do a judicious split through the whole dataset.

  • 09:23

    At the very top level, it'll split the entire dataset into two in a way that doesn't necessarily

  • 09:30

    split out particular classes, but makes it easier when it starts working on each half

  • 09:34

    of the dataset further splitting in a top-down manner in order to try and produce an optimal tree.

  • 09:40

    It will produce trees much better than the one that I just produced with the user classifier.

  • 09:46

    I'd also like you to reflect on what it is we're trying to do here.

  • 09:52

    Given enough time, you could produce a 'perfect' tree for the dataset, but don't forget that

  • 09:57

    the dataset that we've loaded is the training dataset.

  • 10:01

    We're going to evaluate this tree on a different dataset, the test dataset, which hopefully

  • 10:07

    comes from the same source, but is not identical to the training dataset.

  • 10:11

    We're not trying to precisely fit the training dataset;

  • 10:15

    we're trying to fit it in a way that generalizes the kinds of patterns exhibited in the dataset.

  • 10:21

    We're looking for something that will perform well on the test data.

  • 10:26

    That highlights the importance of evaluation in machine learning.

  • 10:32

    That's what this class is going to be about, different ways of evaluating your classifier.

  • 10:37

    That's it.

  • 10:40

    There's some information in the course text about the user classifier, which you can read

  • 10:45

    if you like.

  • 10:47

    Please go on and do the activity associated with this lesson and produce your own classifier.

  • 10:52

    Hopefully, you'll be able to do much better than me given 5-10 minutes.

  • 10:58

    Good luck!

All

The example sentences of JUDICIOUS in videos (1 in total of 1)

when wh-adverb it personal pronoun builds verb, 3rd person singular present its possessive pronoun trees noun, plural , it personal pronoun tries noun, plural to to do verb, base form a determiner judicious adjective split noun, singular or mass through preposition or subordinating conjunction the determiner whole adjective dataset proper noun, singular .

Use "judicious" in a sentence | "judicious" example sentences

How to use "judicious" in a sentence?

  • Judicious praise is to children what the sun is to flowers. Christian Bovee A little praise Goes a great ways.
    -Ralph Waldo Emerson-
  • High finance isn't burglary or obtaining money by false pretenses, but rather a judicious selection from the best features of those fine arts.
    -Finley Peter Dunne-
  • True heroism is minutes, hours, weeks, year upon year of the quiet, precise, judicious exercise of probity and care—with no one there to see or cheer. This is the world.
    -David Foster Wallace-
  • Our love is principle, and has its root In reason, is judicious, manly, free.
    -William Cowper-
  • Zealous men are ever displaying to you the strength of their belief. while judicious men are showing you the grounds of it.
    -William Shenstone-
  • Judicious praise is to children what the sun is to flowers.
    -Christian Nestell Bovee-
  • You can develop good judgment as you do the muscles of the body — by judicious, daily exercise.
    -Grenville Kleiser-
  • A good father believes that he does wisely to encourage enterprise, productive skill, prudent self-denial, and judicious expenditure on the part of his son.
    -William Graham Sumner-

Definition and meaning of JUDICIOUS

What does "judicious mean?"

/jo͞oˈdiSHəs/

adjective
Thoughtful; showing good judgment.

What are synonyms of "judicious"?
Some common synonyms of "judicious" are:
  • wise,
  • sensible,
  • prudent,
  • politic,
  • shrewd,
  • astute,
  • canny,
  • sagacious,
  • common-sense,
  • commonsensical,
  • sound,
  • considered,

You can find detailed definitions of them on this page.

What are antonyms of "judicious"?
Some common antonyms of "judicious" are:
  • injudicious,
  • foolish,
  • ill-advised,

You can find detailed definitions of them on this page.